Search results for: multinomial logistic-AHP

Authors: Chung-Ming Lo, Chung-Chien Lee

Abstract:

In many countries, the lifetime prevalence of shoulder pain is up to 70%. In America, the health care system spends 7 billion per year about the healthy issues of shoulder pain. With respect to the origin, up to 70% of shoulder pain is attributed to rotator cuff lesions This study proposed a computer-aided diagnosis (CAD) system to assist radiologists classifying rotator cuff lesions with less operator dependence. Quantitative features were extracted from the shoulder ultrasound images acquired using an ALOKA alpha-6 US scanner (Hitachi-Aloka Medical, Tokyo, Japan) with linear array probe (scan width: 36mm) ranging from 5 to 13 MHz. During examination, the postures of the examined patients are standard sitting position and are followed by the regular routine. After acquisition, the shoulder US images were drawn out from the scanner and stored as 8-bit images with pixel value ranging from 0 to 255. Upon the sonographic appearance, the boundary of each lesion was delineated by a physician to indicate the specific pattern for analysis. The three lesion categories for classification were composed of 20 cases of tendon inflammation, 18 cases of calcific tendonitis, and 18 cases of supraspinatus tear. For each lesion, second-order statistics were quantified in the feature extraction. The second-order statistics were the texture features describing the correlations between adjacent pixels in a lesion. Because echogenicity patterns were expressed via grey-scale. The grey-scale co-occurrence matrixes with four angles of adjacent pixels were used. The texture metrics included the mean and standard deviation of energy, entropy, correlation, inverse different moment, inertia, cluster shade, cluster prominence, and Haralick correlation. Then, the quantitative features were combined in a multinomial logistic regression classifier to generate a prediction model of rotator cuff lesions. Multinomial logistic regression classifier is widely used in the classification of more than two categories such as the three lesion types used in this study. In the classifier, backward elimination was used to select a feature subset which is the most relevant. They were selected from the trained classifier with the lowest error rate. Leave-one-out cross-validation was used to evaluate the performance of the classifier. Each case was left out of the total cases and used to test the trained result by the remaining cases. According to the physician’s assessment, the performance of the proposed CAD system was shown by the accuracy. As a result, the proposed system achieved an accuracy of 86%. A CAD system based on the statistical texture features to interpret echogenicity values in shoulder musculoskeletal ultrasound was established to generate a prediction model for rotator cuff lesions. Clinically, it is difficult to distinguish some kinds of rotator cuff lesions, especially partial-thickness tear of rotator cuff. The shoulder orthopaedic surgeon and musculoskeletal radiologist reported greater diagnostic test accuracy than general radiologist or ultrasonographers based on the available literature. Consequently, the proposed CAD system which was developed according to the experiment of the shoulder orthopaedic surgeon can provide reliable suggestions to general radiologists or ultrasonographers. More quantitative features related to the specific patterns of different lesion types would be investigated in the further study to improve the prediction.

Keywords: shoulder ultrasound, rotator cuff lesions, texture, computer-aided diagnosis

Procedia PDF Downloads 256

Authors: Trupti Meher, Harihar Sahoo

Abstract:

Premature menopause refers to the occurrence of menopause before the age of 40 years. Women who experience premature menopause either due to biological or induced reasons have a longer duration of exposure to severe symptoms and adverse health consequences when compared to those who undergo menopause at a later age, despite the fact that premature menopause has a profound effect on the health of women. This study attempted to determine the prevalence and predictors of premature menopause among women aged 25-39 years, using data from the National Family Health Survey (NFHS-4) conducted during 2015–16 in India. Descriptive statistics and multinomial logistic regression were used to carry out the result. The results revealed that the prevalence of premature menopause in India was 3.7 percent. Out of which, 2.1 percent of women had experienced natural premature menopause, whereas 1.7 percent had premature surgical menopause. The prevalence of premature menopause was highest in the southern region of India. Further, results of the multivariate model indicated that rural women, women with higher parity, early age at childbearing and women with smoking habits were at a greater risk of premature menopause. A sizeable proportion of women in India are attaining menopause prematurely. Unless due attention is given to this matter, it will emerge as a major problem in India in the future. The study also emphasized the need for further research to enhance knowledge on the problems of premature menopausal women in different socio-cultural settings in India.

Keywords: India, natural menopause, premature menopause, surgical menopause

Procedia PDF Downloads 181

Authors: Leonard Maaya, Michel Meulders, Martina Vandebroek

Abstract:

Discrete Choice Experiments (DCE) are used to investigate how product attributes affect decision-makers’ choices. In DCEs, choice situations consisting of several alternatives are presented from which choice-makers select the preferred alternative. Standard multinomial logit models based on random utility theory can be used to estimate the utilities for the attributes. The overarching principle in these models is that respondents understand and use all the attributes when making choices. However, studies suggest that respondents sometimes ignore some attributes (commonly referred to as Attribute Non-Attendance/ANA). The choice modeling literature presents ANA as a static process, i.e., respondents’ ANA behavior does not change throughout the experiment. However, respondents may ignore attributes due to changing factors like availability of information on attributes, learning/fatigue in experiments, etc. We develop a dynamic mixture latent Markov model to model changes in ANA when information on attributes is provided. The model is illustrated on e-consumers’ webshop choices. The results indicate that the dynamic ANA model describes the behavioral changes better than modeling the impact of information using changes in parameters. Further, we find that providing information on attributes leads to an increase in the attendance probabilities for the investigated attributes.

Keywords: choice models, discrete choice experiments, dynamic models, e-commerce, statistical modeling

Procedia PDF Downloads 110

Authors: Ratu Khabiba, Qisha Quarina

Abstract:

This study aims to analyse the effect of married couples’ assortative educational attainments on the division of economic activities among themselves in the household. This study contributes to the literature on women’s participation in employment, especially among married women, to see whether the traditional values about gender roles in the household still continue to shape the employment participation among married women in Indonesia, despite increasing women’s human capital through education. This study utilizes the Indonesian National Socioeconomic Survey (SUSENAS) 2016 and estimates the results using the multinomial logit model. Our results show that compared to high-educated educational homogamy couples, educational heterogamy couples, especially hypergamy, have a higher probability of being a single-worker type. Moreover, the high-educated educational homogamy couples have the highest probability of being a dual-worker type. Thus, we found evidence that the traditional values of gender role segregation seem to still play a significant role in married women’s employment decision in Indonesia, particularly for couples’ with educational heterogamy and low-educated educational homogamy couples.

Keywords: assortative education, dual-worker, hypergamy, homogamy, traditional values, women labor participation

Procedia PDF Downloads 98

Authors: Doki Naomi Onyeje, Doki Gowon Ama

Abstract:

The past 4 years have been traumatic for Nigerians, having to deal with a number of complex economic issues with dire consequences for the economy. Households have had to respond variously to some of these problems in peculiar ways, depending, of course, on the nature and character of a particular shock. The type, magnitude, intensity and duration of a particular shock might be the determinant of different household responses. While households’ responses to the Global Financial Crisis and Covid 19 Pandemic have been documented by researchers, other economic shocks have continued to emerge in Nigeria. The dramatic turn of events since coming on board of the new government on May 29th 2023, has introduced a new economic twist that households will have to adjust to. This study, therefore, sets out to examine household responses by disaggregating them by their livelihood sources. A survey of 420 households across North Central Nigeria will be done to generate information on the respective responses. A Multinomial logit regression analysis will be employed to test the hypothesis that livelihood source(s) influences household responses to economic shocks. Consequently, responses from public and private households will be examined. The expected results should be that household responses might have some similarities, but it is expected that some peculiar responses across groups will emerge and these differences will guide for group-specific interventions. The Theatre for Development (TfD) approach will be used to disseminate and propagate results from this study to and among stakeholders for effective policy frameworks.

Keywords: drama, dynamics, economic shocks, household responses, Nigeria

Procedia PDF Downloads 45

Authors: Benjamas Penboon, Zachary Zimmer, Aree Jampaklay

Abstract:

Cambodia is a country where labor migration has been consistently high. Coupled with advancing labor opportunities in urban areas, a function partly of globalization, this is resulting in massive migration out of rural areas. This is particularly true in Cambodia where there are high migration and a very large proportion of adult children living some distant from their parents. This paper explores characteristics associated with migrant providing support to parents in rural Cambodia. With reference to perspectives of family altruism and solidarity, this analysis particularly focusses on how a series of variables representing family integration and residential location associates with intergenerational monetary and instrumental support from migrants. The study hypothesizes that migrants are more likely to provide support when parents are in need, and there are no alternative means of support. Data come from The Rural Household Survey (N=3,713), part of the 2011 Cambodian Rural Urban Migration Project (CRUMP). Multilevel multinomial models indicate international migrants are likely to give money, while internal migrants are likely to provide both money and instrumental support, especially when migrants have no sibling and their parent in poor health status. In addition, employed migrants are two times providing monetary compared to those unemployed. Findings elucidate the decision to which and why support occurs more often when no other source of support exists and also depends on the ability to provide of migrants themselves.

Keywords: migration, left-behind parent, intergenerational relations, support, rural, Cambodia

Procedia PDF Downloads 144

Authors: Jie Liu, Wei Wei, Chun-Ping Chang

Abstract:

Using a sample of 110 countries over the period 1984-2013, this paper examines the impacts of country risks on choosing a specific exchange rate regime (first by utilizing the Levy-Yeyati and Sturzenegger de facto classification and then robusting it by the IMF de jure measurement) relative to other regimes via the panel multinomial logit approach. Empirical findings are as follows. First, in the full samples case we provide evidence that government is more likely to implement a flexible regime, but less likely to adopt a fixed regime, under a low level of composite and financial risk. Second, we find that Eurozone countries are more likely to choose a fixed exchange rate regime with a decrease in the level of country risk and favor a flexible regime in response to a shock from an increase of risk, which is opposite to non-Eurozone countries. Third, we note that high-risk countries are more likely to choose a fixed regime with a low level of composite and political risk in the government, but do not adjust the exchange rate regime as a shock absorber when facing economic and financial risks. It is interesting to see that those countries with relatively low risk display almost opposite results versus high-risk economies. Overall, we believe that it is critically important to account for political economy variables in a government’s exchange rate policy decisions, especially for country risks. All results are robust to the panel ordered probit model.

Keywords: country risk, political economy, exchange rate regimes, shock absorber

Procedia PDF Downloads 278

Authors: Javad Izadi, Sahar Majioud

Abstract:

This study presents an approach of assessing the choice of performance measures of companies in the United Kingdom after the application of IFRS in 2005. The aim of this study is to investigate the effects of IFRS on the choice of performance evaluation methods for UK companies. We analyse through an econometric model the relationship of the dependent variable, the firm’s performance, which is a nominal variable with the independent ones. Independent variables are split into two main groups: the first one is the group of accounting-based measures: Earning per share, return on assets and return on equities. The second one is the group of market-based measures: market value of property plant and equipment, research and development, sales growth, market to book value, leverage, segment and size of companies. Concerning the regression used, it is a multinomial logistic regression performed on a sample of 130 UK listed companies. Our finding shows after IFRS adoption, and companies give more importance to some variables such as return on equities and sales growth to assess their performance, whereas the return on assets and market to book value ratio does not have as much importance as before IFRS in evaluating the performance of companies. Also, there are some variables that have no impact on the performance measures anymore, such as earning per share. This article finding is empirically important for business in subjects related to IFRS and companies’ performance measurement.

Keywords: performance’s Measure, nominal variable, econometric model, evaluation methods

Procedia PDF Downloads 119

Authors: Sushma Ghogale

Abstract:

With a surge in user-generated content or feedback or reviews on the internet, it has become possible and important to know consumers' opinions about products and services. This data is important for both potential customers and businesses providing the services. Data from social media is attracting significant attention and has become the most prominent channel of expressing an unregulated opinion. Prospective customers look for reviews from experienced customers before deciding to buy a product or service. Several websites provide a platform for users to post their feedback for the provider and potential customers. However, the biggest challenge in analyzing such data is in extracting latent features and providing term-level analysis of the data. This paper proposes an approach to use topic modeling to classify the reviews into topics and conduct sentiment analysis to mine the opinions. This approach can analyse and classify latent topics mentioned by reviewers on business sites or review sites, or social media using topic modeling to identify the importance of each topic. It is followed by sentiment analysis to assess the satisfaction level of each topic. This approach provides a classification of hotel reviews using multiple machine learning techniques and comparing different classifiers to mine the opinions of user reviews through sentiment analysis. This experiment concludes that Multinomial Naïve Bayes classifier produces higher accuracy than other classifiers.

Keywords: latent Dirichlet allocation, topic modeling, text classification, sentiment analysis

Procedia PDF Downloads 76

Authors: A. Alhusban, M. Alqawasmeh, F. Alfawares

Abstract:

Introduction: Diabetes is a chronic health problem and a major risk factor of stroke. A number of therapeutic modalities exist for diabetes management. It’s still unknown whether the different oral hypoglycemic agents would ameliorate the detrimental effect of diabetes on stroke severity. The objective of this work is to assess the effect of pretreatment with oral hypoglycemic agents, insulin and their combination on stroke severity at presentation. Patients and Methods: Patients admitted to the King Abdullah University Hospital (KAUH)-Jordan with ischemic stroke between January 2015 and December 2016 were evaluated and their comorbid diseases, treatment on admission and their neurologic severity was assessed using the National Institute of Health Stroke Scale (NIHSS) were documented. Stroke severity was compared for non-diabetic patients and diabetic patients treated with different antidiabetic agents. Results: Data from 324 patients with acute stroke was documented. The median age of participants was 69 years. Diabetes was documented in about 50% of the patients. Multinomial regression analysis identified diabetes treatment status as an independent predictor of neurological severity of stroke (p=0.032). Patients treated with oral hypoglycemic agents had a significantly lower NIHSS as compared to nondiabetic patients and insulin treated patients (p < 0.02). The positive effect of oral hypoglycemic agents was blunted by insulin co-treatment. Insulin did not alter the severity of stroke as compared to non-diabetics. Conclusion: Oral hypoglycemic agents may reduce the severity of neurologic deficit of ischemic stroke and may have neuroprotective effect.

Keywords: diabetes, stroke, neuroprotection, oral hypoglycemic agents

Procedia PDF Downloads 138

Authors: Jiahui Yang, John Quigley, Lesley Walls

Abstract:

In this paper, the authors develop a stochastic model regarding the investment in supplier delivery performance development from a buyer’s perspective. The authors propose a multivariate model through a Multinomial-Dirichlet distribution within an Empirical Bayesian inference framework, representing both the epistemic and aleatory uncertainties in deliveries. A closed form solution is obtained and the lower and upper bound for both optimal investment level and expected profit under uncertainty are derived. The theoretical properties provide decision makers with useful insights regarding supplier delivery performance improvement problems where multiple delivery statuses are involved. The authors also extend the model from a single supplier investment into a supplier portfolio, using a Lagrangian method to obtain a theoretical expression for an optimal investment level and overall expected profit. The model enables a buyer to know how the marginal expected profit/investment level of each supplier changes with respect to the budget and which supplier should be invested in when additional budget is available. An application of this model is illustrated in a simulation study. Overall, the main contribution of this study is to provide an optimal investment decision making framework for supplier development, taking into account multiple delivery statuses as well as multiple projects.

Keywords: decision making, empirical bayesian, portfolio optimization, supplier development, supply chain management

Procedia PDF Downloads 269

Authors: Ada Garus

Abstract:

This paper presents the outcomes of the sustainability assessment of food delivery with a last-mile delivery service introduced in a real-world case study. The methodology used in the sustainability assessment integrates multi-criteria decision-making analysis, sustainability pillars, and scenario analysis to best reflect the conflicting needs of stakeholders involved in the last mile delivery system. The case study provides an application of the framework to the food delivery system of the Joint Research Centre of the European Commission where three alternative solutions were analyzed I) the existent state in which individuals frequent the local cantine or pick up their food, using their preferred mode of transport II) the hypothetical scenario in which individuals can only order their food using the delivery droid system III) a scenario in which the food delivery droid based system is introduced as a supplement to the current system. The environmental indices are calculated using a simulation study in which decision regarding the food delivery is predicted using a multinomial logit model. The vehicle dynamics model is used to predict the fuel consumption of the regular combustion engines vehicles used by the cantine goers and the electricity consumption of the droid. The sustainability assessment allows for the evaluation of the economic, environmental, and social aspects of food delivery, making it an apt input for policymakers. Moreover, the assessment is one of the first studies to investigate automated delivery droids, which could become a frequent addition to the urban landscape in the near future.

Keywords: innovations in transportation technologies, behavioural change and mobility, urban freight logistics, innovative transportation systems

Procedia PDF Downloads 173

Authors: Rohini Hariharan, Yazhini R., Blessy Maria Mathew

Abstract:

The task of detecting email spam is a very important one in the era of digital technology that needs effective ways of curbing unwanted messages. This paper presents an approach aimed at making email spam categorization algorithms transparent, reliable and more trustworthy by incorporating Local Interpretable Model-agnostic Explanations (LIME). Our technique assists in providing interpretable explanations for specific classifications of emails to help users understand the decision-making process by the model. In this study, we developed a complete pipeline that incorporates LIME into the spam classification framework and allows creating simplified, interpretable models tailored to individual emails. LIME identifies influential terms, pointing out key elements that drive classification results, thus reducing opacity inherent in conventional machine learning models. Additionally, we suggest a visualization scheme for displaying keywords that will improve understanding of categorization decisions by users. We test our method on a diverse email dataset and compare its performance with various baseline models, such as Gaussian Naive Bayes, Multinomial Naive Bayes, Bernoulli Naive Bayes, Support Vector Classifier, K-Nearest Neighbors, Decision Tree, and Logistic Regression. Our testing results show that our model surpasses all other models, achieving an accuracy of 96.59% and a precision of 99.12%.

Keywords: text classification, LIME (local interpretable model-agnostic explanations), stemming, tokenization, logistic regression.

Procedia PDF Downloads 21

Authors: A. Alhusban, M. Alqawasmeh, F. Alfawares

Abstract:

Introduction: Despite improvements in stroke management, it remains the leading cause of disability worldwide. It has been suggested that enhancing brain angiogenesis after stroke will improve stroke outcome. Promoting post stroke angiogenesis requires the upregulation of angiogenic factors with a simultaneous reduction of anti-angiogenic factors. Thrombospondin-1 is the main anti-angiogenic protein in the living cells. Counterintuitively, it has been shown that animals with Thrombospondin-1 knockdown will have better stroke outcome. Data about the clinical significance of Thrombspondin-1 levels at the time of admission is still lacking. The objective of this work is to assess the association between serum Thrombospondin-1 levels measured at the time of admission and baseline neurologic severity after stroke. Patients and Methods: Blood samples were collected from patients admitted to the King Abdullah University Hospital (KAUH) with ischemic stroke at the time of admission and serum Thrombopsondin-1 levels were measured using ELISA. Patients neurologic severity was evaluated using the National Institute of Health Stroke Scale (NIHSS). Results: Samples from 50 patients admitted between January 2016 and December 2016 were collected. The median age of participants was 68 years and the median NIHSS was 3. Multinomial regression identified serum Thrombospondin-1 as an independent predictor of stroke outcome (p=0.003). Baseline serum Thrombsopondin-1 was negatively associated with NIHSS at the time of admission (spearman rho correlation coefficient=0.272, p=0.032). Conclusion: Serum Thrombospondin-1 at the time of admission may be a useful marker of stroke severity that predicts more severe neurologic severity.

Keywords: thrombospondin, stroke, neuroprotection, biomarkers

Procedia PDF Downloads 113

Authors: Narges Ebadi, Davod Ahmadi, Hiliary Monteith, Hugo Melgar-Quinonez

Abstract:

Migration cannot necessarily relieve pressure on water resources in origin communities, and male out-migration can increase the water management burden of women. However, inflows of financial remittances seem to offer possibilities of investing in improving drinking-water access. Therefore, remittances may be an important pathway for migrants to support water security. This paper explores the association between water access and the receipt of remittances in households in sub-Saharan Africa. Data from round 6 of the 'Afrobarometer' surveys in 2016 were used (n= 49,137). Descriptive, bivariate and multivariate statistical analyses were carried out in this study. Regardless of country, findings from descriptive analyses showed that approximately 80% of the respondents never received remittance, and 52% had enough clean water. Only one-fifth of the respondents had piped water supply inside the house (19.9%), and approximately 25% had access to a toilet inside the house. Bivariate analyses revealed that even though receiving remittances was significantly associated with water supply, the strength of association was very weak. However, other factors such as the area of residence (rural vs. urban), cash income frequencies, electricity access, and asset ownership were strongly associated with water access. Results from unadjusted multinomial logistic regression revealed that the probability of having no access to piped water increased among remittance recipients who received financial support at least once a month (OR=1.324) (p < 0.001). In contrast, those not receiving remittances were more likely to regularly have a water access concern (OR=1.294) (p < 0.001), and not have access to a latrine (OR=1.665) (p < 0.001). In conclusion, receiving remittances is significantly related to water access as the strength of odds ratios for socio-demographic factors was stronger.

Keywords: remittances, water access, SSA, migration

Procedia PDF Downloads 147

Authors: Roselyn Chipojola, Shu-yu Kuo

Abstract:

Background: Breastfeeding self-efficacy in both mothers and fathers play a crucial role in improving exclusive breastfeeding rates. However, less is known on the relationship and predictors of paternal and maternal breastfeeding self-efficacy. This study aimed to examine the relationship and associated factors of breastfeeding self-efficacy (BSE) among mothers and fathers in Malawi. Methods: A cross-sectional study was conducted on 180 pairs of postpartum mothers and fathers at a tertiary maternity facility in central Malawi. BSE was measured using the Breastfeeding Self-Efficacy Scale Short-Form. Depressive symptoms were assessed by the Edinburgh Postnatal Depression Scale. A structured questionnaire was used to collect demographic and health variables. Data were analyzed using multivariable logistic regression and multinomial logistic regression. Results: A higher score of self-efficacy was found in mothers (mean=55.7, Standard Deviation (SD) =6.5) compared to fathers (mean=50.2, SD=11.9). A significant association between paternal and maternal breastfeeding self-efficacy was found (r= 0. 32). Age, employment status, mode of birth was significantly related to maternal and paternal BSE, respectively. Older age and caesarean section delivery were significant factors of combined BSE scores in couples. A higher BSE score in either the mother or her partner predicted higher exclusive breastfeeding rates. BSE scores were lower when couples’ depressive symptoms were high. Conclusion: BSE are highly correlated between Malawian mothers and fathers, with a relatively higher score in maternal BSE. Importantly, a high BSE in couples predicted higher odds of exclusive breastfeeding, which highlights the need to include both mothers and fathers in future breastfeeding promotion strategies.

Keywords: paternal, maternal, exclusive breastfeeding, breastfeeding self‑efficacy, malawi

Procedia PDF Downloads 46

Authors: Roien Qiam, Shoshi Mizokami

Abstract:

Parking demand in the Central Business District (CBD) has enlarged with the increase of the number of private vehicles due to rapid economic growth, lack of an efficient public transport and traffic management system. This has resulted in low mobility, poor accessibility, serious congestion, high rates of traffic accident fatalities and injuries and air pollution, mainly because people have to drive slowly around to find a vacant spot. With parking pricing and enforcement policy, considerable advancement could be found, and on-street parking spaces could be managed efficiently and effectively. To evaluate parking demand and making parking policy, it is required to understand the current parking condition and driver’s behavior, understand how drivers choose their parking type and location as well as their behavior toward finding a vacant parking spot under parking charges and search times. This study illustrates the result from an observational, revealed and stated preference surveys and experiment. Attained data shows that there is a gap between supply and demand in parking and it has maximized. For the modeling of the parking decision, a choice model was constructed based on discrete choice modeling theory and multinomial logit model estimated by using SP survey data; the model represents the choice of an alternative among different alternatives which are priced on-street, off-street, and illegal parking. Individuals choose a parking type based on their preference concerning parking charges, searching times, access times and waiting times. The parking assignment model was obtained directly from behavioral model and is used in parking simulation. The study concludes with an evaluation of parking policy.

Keywords: CBD, parking demand forecast, parking policy, parking choice model

Procedia PDF Downloads 169

Authors: Lavanya Annadi, Fahimeh Jafari

Abstract:

Transportation brings immense benefits to society, but it also has its costs. Costs include such as the cost of infrastructure, personnel and equipment, but also the loss of life and property in traffic accidents on the road, delays in travel due to traffic congestion and various indirect costs in terms of air transport. More research has been done to identify the various factors that affect road accidents, such as road infrastructure, traffic, sociodemographic characteristics, land use, and the environment. The aim of this research is to predict the probabilistic crash prediction of vehicles using machine learning due to natural and structural reasons by excluding spontaneous reasons like overspeeding etc., in the United States. These factors range from weather factors, like weather conditions, precipitation, visibility, wind speed, wind direction, temperature, pressure, and humidity to human made structures like road structure factors like bump, roundabout, no exit, turning loop, give away, etc. Probabilities are dissected into ten different classes. All the predictions are based on multiclass classification techniques, which are supervised learning. This study considers all crashes that happened in all states collected by the US government. To calculate the probability, multinomial expected value was used and assigned a classification label as the crash probability. We applied three different classification models, including multiclass Logistic Regression, Random Forest and XGBoost. The numerical results show that XGBoost achieved a 75.2% accuracy rate which indicates the part that is being played by natural and structural reasons for the crash. The paper has provided in-deep insights through exploratory data analysis.

Keywords: road safety, crash prediction, exploratory analysis, machine learning

Procedia PDF Downloads 81

Authors: Linnan Zhang

Abstract:

Linguists, as well as psychologists, have shown great interests in implicit causality in reference processing. However, most frequently-used approaches to this issue are psychological experiments (such as eye tracking or self-paced reading, etc.). This research is a corpus-based one and is assisted with statistical tool – software R. The main focus of the present study is about the competition between verb-based implicit causality and theme structure’s influence on anaphora bias in Mandarin Chinese sentences. In Accessibility Theory, it is believed that salience, which is also known as accessibility, and relevance are two important factors in reference processing. Theme structure, which is a special syntactic structure in Chinese, determines the salience of an antecedent on the syntactic level while verb-based implicit causality is a key factor to the relevance between antecedent and anaphora. Therefore, it is a study about anaphora, combining psychology with linguistics. With analysis of the sentences from corpus as well as the statistical analysis of Multinomial Logistic Regression, major findings of the present study are as follows: 1. When the sentence is stated in a ‘cause-effect’ structure, the theme structure will always be the antecedent no matter forward biased verbs or backward biased verbs co-occur; in non-theme structure, the anaphora bias will tend to be the opposite of the verb bias; 2. When the sentence is stated in a ‘effect-cause’ structure, theme structure will not always be the antecedent and the influence of verb-based implicit causality will outweigh that of theme structure; moreover, the anaphora bias will be the same with the bias of verbs. All the results indicate that implicit causality functions conditionally and the noun in theme structure will not be the high-salience antecedent under any circumstances.

Keywords: accessibility theory, anaphora, theme strcture, verb-based implicit causality

Procedia PDF Downloads 173

Authors: Rocio Herrero Romero, Lucie Cluver, James Hall, Janina Steinert

Abstract:

Educational delay and non-completion are major policy concerns in South Africa. However, little research has focused on predictors for educational delay amongst adolescents in disadvantaged areas. This study has two aims: first, to use data integration approaches to compare the educational delay of 599 adolescents aged 16 to 18 from disadvantaged communities to national and provincial representative estimates in South Africa. Second, the paper also explores predictors for educational delay by comparing adolescents out of school (n=64) and at least one year behind (n=380), with adolescents in the age-appropriate grade or higher (n=155). Multinomial logistic regression models using self-report and administrative data were applied to look for significant associations of risk and protective factors. Significant risk factors for being behind (rather than in age-appropriate grade) were: male gender, past grade repetition, rural location and larger school size. Risk factors for being out of school (rather than in the age-appropriate grade) were: past grade repetition, having experienced problems concentrating at school, household poverty, and food insecurity. Significant protective factors for being in the age-appropriate grade (rather than out of school) were: living with biological parents or grandparents and access to school counselling. Attending school in wealthier communities was a significant protective factor for being in the age-appropriate grade (rather than behind). Our results suggest that both personal and contextual factors –family and school- predicted educational delay. This study provides new evidence to the significant effects of personal, family, and school characteristics on the educational outcomes of adolescents from disadvantaged communities in South Africa. This is the first longitudinal and quantitative study to systematically investigate risk and protective factors for post-compulsory educational outcomes amongst South African adolescents living in disadvantaged communities.

Keywords: disadvantaged communities, quantitative analysis, school delay, South Africa

Procedia PDF Downloads 321

Authors: A. Rezazadeh, N. Omidvar, H. Eini-Zinab

Abstract:

Food insecurity (FI) influences may result in poor physical and mental health outcomes. Minor ethnic group may experience higher level of FI, and this situation may be related with higher depression prevalence. The aim of this study was to determine the association of depression with food security status in major (Azeri) and minor (Kurdish) ethnicity living in Urmia, West Azerbaijan, north of Iran. In this cross-sectional study, 723 participants (427 women and 296 men) aged 20–64 years old, from two ethnic groups (445 Azeri and 278 Kurdish), were selected through a multi stage cluster systematic sampling. Depression rate was assessed by “Beck” short form questionnaire (validated in Iranians) through interviews. Household FI status (HFIS) was measured using adapted HFI access scale through face-to-face interviews at homes. Multinomial logistic regression was used to estimate odds ratios (OR) of depression across HFIS. Higher percent of Kurds had moderate and severe depression in comparison with Azeri group (73 [17.3%] vs. 86 [27.9%]). There were not any significant differences between the two ethnicities in mild depression. Also, of all the subjects, moderate-to-sever FI was more prevalent in Kurds (28.5%), compared to Azeri group (17.3%) [P < 0.01]. Kurdish ethnic group living in food security or mild FI households had lower chance to have symptom of severe depression in comparison to those with sever FI (OR=0.097; 95% CI: 0.02-0.47). However, there was no significant association between depression and HFI in Azeri group. Findings revealed that the severity of HFI was related with severity depression in minor studied ethnic groups. However, in Azeri ethnicity as a major group, other confounders may have influence on the relation with depression and FI, that were not studied in the present study.

Keywords: depression, ethnicity, food security status, Iran

Procedia PDF Downloads 183

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health-related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores to text, ranging from positive, neutral, and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing and tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial, and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced, and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process and substituting the Naive Bayes for a deep learning neural network model.

Keywords: sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model

Procedia PDF Downloads 71

Authors: Chimuanya Osuji, Kido Uyamasi, Morgan Bradley

Abstract:

Introduction: Obesity is a major risk factor for many chronic diseases, with higher rates occurring among certain populations. Even though disparities in obesity rates exist for those with disabilities, few studies have assessed the association between disability and obesity status. This study aims to examine the association between type of disability and obesity status among US adults during the Covid-19 pandemic (2019-2021). Methods: Data for this cross-sectional study was obtained from the 2019, 2020 and 2021 NHIS. Multinomial logistic regressions were used to assess the relationship between each type of disability and obesity status (reference= normal/underweight). Each model adjusted for demographic, health status and health-related quality of life variables. Statistical analyses were conducted using SAS version 9.4. Results: Of the 82,632 US adults who completed the NHIS in 2019, 2020, and 2021. 8.9% (n= 7,354) reported at least 1 disability-related condition. Respondents reported having a disability across vision (1.5%), hearing (1.5%), mobility (5.3%), communication (0.8%), cognition (2.4%) and self-care (1.1%) domains. After adjusting for covariates, adults with at least 1 disability-related condition were about 30% more likely to have moderate-severe obesity (AOR=1.3; 95% CI=1.11, 1.53). Mobility was the only disability category positively associated with mild obesity (AOR=1.16; 95% CI=1.01, 1.35) and moderate/severe obesity (AOR=1.6; 95% CI=1.35, 1.89). Individuals with vision disability were about 35% less likely to have mild obesity (AOR=0.66; 95% CI=0.51, 0.86) and moderate-severe obesity (AOR=0.66; 95% CI= 0.48, 0.9). Individuals with hearing disability were 28% less likely to have mild obesity (AOR=0.72; 95% CI= 0.56, 0.94). Individuals with communication disability were about 30% less likely to be overweight (AOR=0.66; 95% CI=0.47, 0.93) and 50% less likely to have mild obesity (AOR=0.45; 95% CI= 0.29, 0.71). Individuals with cognitive disability were about 25% less likely to have mild obesity and about 35% less likely to have moderate-severe obesity. Individuals with self-care disability were about 30% less likely to be overweight. Conclusion: Mobility-related disabilities are significantly associated with obesity status among adults residing in the United States. Researchers and policy makers should implement obesity intervention methods that can address the gap in obesity prevalence rates among those with and without disabilities.

Keywords: cognition, disability, mobility, obesity

Procedia PDF Downloads 36

Authors: Kita R. Ashman, Anthony R. Rendall, Matthew R. E. Symonds, Desley A. Whisson

Abstract:

Forest cover is decreasing globally, chiefly due to the conversion of forest to agricultural landscapes. In contrast, the area under plantation forestry is increasing significantly. For wildlife occupying landscapes where native forest is the dominant land cover, plantations generally represent a lower value habitat; however, plantations established on land formerly used for pasture may benefit wildlife by providing temporary forest habitat and increasing connectivity. This study investigates the influence of landscape, site, and climatic factors on koala population density in far south-west Victoria where there has been extensive plantation establishment. We conducted koala surveys and habitat characteristic assessments at 72 sites across three habitat types: plantation, native vegetation blocks, and native vegetation strips. We employed a hierarchical modeling framework for estimating abundance and constructed candidate multinomial N-mixture models to identify factors influencing the abundance of koalas. We detected higher mean koala density in plantation sites (0.85 per ha) than in either native block (0.68 per ha) or native strip sites (0.66 per ha). We found five covariates of koala density and using these variables, we spatially modeled koala abundance and discuss factors that are key in determining large-scale distribution and density of koala populations. We provide a distribution map that can be used to identify high priority areas for population management as well as the habitat of high conservation significance for koalas. This information facilitates the linkage of ecological theory with the on-ground implementation of management actions and may guide conservation planning and resource management actions to consider overall landscape configuration as well as the spatial arrangement of plantations adjacent to the remnant forest.

Keywords: abundance modelling, arboreal mammals plantations, wildlife conservation

Procedia PDF Downloads 89

Authors: Xiaomin Zhong, Alexander Pate, Ya-Ting Yang, Ali Fahmi, Darren M. Ashcroft, Ben Goldacre, Brian Mackenna, Amir Mehrkar, Sebastian C. J. Bacon, Jon Massey, Louis Fisher, Peter Inglesby, Kieran Hand, Tjeerd van Staa, Victoria Palin

Abstract:

Background: This study aimed to predict risks of potentially inappropriate antibiotic type and repeat prescribing and assess changes during COVID-19. Methods: With the approval of NHS England, we used the OpenSAFELY platform to access the TPP SystmOne electronic health record (EHR) system and selected patients prescribed antibiotics from 2019 to 2021. Multinomial logistic regression models predicted the patient’s probability of receiving an inappropriate antibiotic type or repeating the antibiotic course for each common infection. Findings: The population included 9.1 million patients with 29.2 million antibiotic prescriptions. 29.1% of prescriptions were identified as repeat prescribing. Those with same-day incident infection coded in the EHR had considerably lower rates of repeat prescribing (18.0%), and 8.6% had a potentially inappropriate type. No major changes in the rates of repeat antibiotic prescribing during COVID-19 were found. In the ten risk prediction models, good levels of calibration and moderate levels of discrimination were found. Important predictors included age, prior antibiotic prescribing, and region. Patients varied in their predicted risks. For sore throat, the range from 2.5 to 97.5th percentile was 2.7 to 23.5% (inappropriate type) and 6.0 to 27.2% (repeat prescription). For otitis externa, these numbers were 25.9 to 63.9% and 8.5 to 37.1%, respectively. Interpretation: Our study found no evidence of changes in the level of inappropriate or repeat antibiotic prescribing after the start of COVID-19. Repeat antibiotic prescribing was frequent and varied according to regional and patient characteristics. There is a need for treatment guidelines to be developed around antibiotic failure and clinicians provided with individualised patient information.

Keywords: antibiotics, infection, COVID-19 pandemic, antibiotic stewardship, primary care

Procedia PDF Downloads 81

Authors: Peiyin Hung, Katy Kozhimannil, Michelle Casey, Ira Moscovice

Abstract:

Background/Objective: The loss of obstetric services has been a pressing concern in urban and rural areas nationwide. This study aims to determine factors that contribute to the loss of obstetric care through closures of a hospital or obstetric unit. Methods: Data from 2002-2013 American Hospital Association annual surveys were used to identify hospitals providing obstetric services. We linked these data to Medicare Healthcare Cost Report Information for hospital financial indicators, the US Census Bureau’s American Community Survey for zip-code level characteristics, and Area Health Resource files for county- level clinician supply measures. A discrete-time multinomial logit model was used to determine contributing factors to obstetric unit or hospital closures. Results: Of 3,551 hospitals providing obstetrics services during 2002-2013, 82% kept units open, 12% stopped providing obstetrics services, and 6% closed down completely. State-level variations existed. Factors that significantly increased hospitals’ probability of obstetric unit closures included lower than 250 annual birth volume (adjusted marginal effects [95% confidence interval]=34.1% [28%, 40%]), closer proximity to another hospital with obstetric services (per 10 miles: -1.5% [-2.4, -0.5%]), being in a county with lower family physician supply (-7.8% [-15.0%, -0.6%), being in a zip code with higher percentage of non-white females (per 10%: 10.2% [2.1%, 18.3%]), and with lower income (per $1,000 income: -0.14% [-0.28%, -0.01%]). Conclusions: Over the past 12 years, loss of obstetric services has disproportionately affected areas served by low-volume urban and rural hospitals, non-white and low-income communities, and counties with fewer family physicians, signaling a need to address maternity care access in these communities.

Keywords: access to care, obstetric care, service line discontinuation, hospital, obstetric unit closures

Procedia PDF Downloads 202

Authors: Juan Francisco Reinoso Gordo, Francisco Javier Ariza-López, José Rodríguez Avi, Domingo Barrera Rosillo

Abstract:

The evaluation of the quality of a data product is based on the comparison of the product with a reference of greater accuracy. In the case of MDE data products, quality assessment usually focuses on positional accuracy and few studies consider other terrain characteristics, such as slope and orientation. The proposal that is made consists of evaluating the similarity of two DEMs (a product and a reference), through the joint analysis of the distribution functions of the variables of interest, for example, elevations, slopes and orientations. This is a multivariable approach that focuses on distribution functions, not on single parameters such as mean values or dispersions (e.g. root mean squared error or variance). This is considered to be a more holistic approach. The use of the Kolmogorov-Smirnov test is proposed due to its non-parametric nature, since the distributions of the variables of interest cannot always be adequately modeled by parametric models (e.g. the Normal distribution model). In addition, its application to the multivariate case is carried out jointly by means of a single test on the convolution of the distribution functions of the variables considered, which avoids the use of corrections such as Bonferroni when several statistics hypothesis tests are carried out together. In this work, two DEM products have been considered, DEM02 with a resolution of 2x2 meters and DEM05 with a resolution of 5x5 meters, both generated by the National Geographic Institute of Spain. DEM02 is considered as the reference and DEM05 as the product to be evaluated. In addition, the slope and aspect derived models have been calculated by GIS operations on the two DEM datasets. Through sample simulation processes, the adequate behavior of the Kolmogorov-Smirnov statistical test has been verified when the null hypothesis is true, which allows calibrating the value of the statistic for the desired significance value (e.g. 5%). Once the process has been calibrated, the same process can be applied to compare the similarity of different DEM data sets (e.g. the DEM05 versus the DEM02). In summary, an innovative alternative for the comparison of DEM data sets based on a multinomial non-parametric perspective has been proposed by means of a single Kolmogorov-Smirnov test. This new approach could be extended to other DEM features of interest (e.g. curvature, etc.) and to more than three variables

Keywords: data quality, DEM, kolmogorov-smirnov test, multivariate DEM comparison

Procedia PDF Downloads 91

Authors: Hussien Ali, Mesfin Menza, Fitsum Hagos, Amare Haileslassie

Abstract:

Climate change has perverse effects on agricultural productivity and natural resource base, negatively affecting the well-being of the households and communities. The government and NGOs promote climate smart agricultural (CSA) practices to help farmers adapt to and mitigate the negative effects of climate change. This study aims to identify widely available CSA practices and examine their impacts on food security and multi-dimensional poverty of rural farm households in the Central Rift Valley, Ethiopia. Using three-stage proportional to size sampling procedure, the study randomly selected 278 households from two kebeles from four districts each. A cross-sectional data of 2020/21 cropping season was collected using structured and pretested survey questionnaire. Food consumption score, dietary diversity score, food insecurity experience scale, and multidimensional poverty index were calculated to measure households’ welfare indicators. Multinomial endogenous switching regression model was used to assess average treatment effects of CSA on these outcome indicators on adopter and non-adopter households. The results indicate that the widely adopted CSA practices in the area are conservation agriculture, soil fertility management, crop diversification, and small-scale irrigation. Adopter households have, on average, statistically higher food consumption score, dietary diversity score and lower food insecurity access scale than non-adopters. Moreover, adopter households, on average, have lower deprivation score in multidimensional poverty compared to non-adopter households. Up scaling the adoption of CSA practices through the improvement of households’ implementation capacity and better information, technical advice, and innovative financing mechanisms is advised. Up scaling CSA practices can further promote achieving global goals such as SDG 1, SDG 2, and SDG 13 targets, aimed to end poverty and hunger and mitigate the adverse impacts of climate change, respectively.

Keywords: climate-smart agriculture, food security, multidimensional poverty, upscaling CSA, Ethiopia

Procedia PDF Downloads 62

Authors: Idit Kalisher, Israel Luski

Abstract:

One result of the growing dynamicity of labor markets in recent decades is a wider scope of employment mobility – i.e., transitions between employers, either within or between careers. Employment mobility decisions are primarily affected by the current employment status of the worker, which is reflected in wage and tenure. Using 34,328 observations from the National Longitudinal Survey of Youth 1979 (NLS79), which were derived from the USA population between 1990 and 2012, this paper aims to investigate the effects of wage and tenure over employment mobility choices, and additionally to examine the effects of other personal characteristics, individual labor market characteristics and macroeconomic factors. The estimation strategy was designed to address two challenges that arise from the combination of the model and the data: (a) endogeneity of the wage and the tenure in the choice equation; and (b) unobserved heterogeneity, as the data of this research is longitudinal. To address (a), estimation was performed using two-stage limited dependent variable procedure (2SLDV); and to address (b), the second stage was estimated using femlogit – an implementation of the multinomial logit model with fixed effects. Among workers who have experienced at least one turnover, the wage was found to have a main effect on career turnover likelihood of all workers, whereas the wage effect on job turnover likelihood was found to be dependent on individual characteristics. The wage was found to negatively affect the turnover likelihood and the effect was found to vary across wage level: high-wage workers were more affected compared to low-wage workers. Tenure was found to have a main positive effect on both turnover types’ likelihoods, though the effect was moderated by the wage. The findings also reveal that as their wage increases, women are more likely to turnover than men, and academically educated workers are more likely to turnover within careers. Minorities were found to be as likely as Caucasians to turnover post wage-increase, but less likely to turnover with each additional tenure year. The wage and the tenure effects were found to vary also between careers. The difference in attitude towards money, labor market opportunities and risk aversion could explain these findings. Additionally, the likelihood of a turnover was found to be affected by previous unemployment spells, age, and other labor market and personal characteristics. The results of this research could assist policymakers as well as business owners and employers. The former may be able to encourage women and older workers’ employment by considering the effects of gender and age on the probability of a turnover, and the latter may be able to assess their employees’ likelihood of a turnover by considering the effects of their personal characteristics.

Keywords: employment mobility, endogeneity, femlogit, turnover

Procedia PDF Downloads 123

Authors: Yi-Tung Lin

Abstract:

Researchers commonly assess implicit self-esteem with the Implicit Association Test (IAT). The IAT’s measure, often referred to as the IAT effect, indicates the strengths of automatic preferences for the self relative to others, which is often considered an index of implicit self-esteem. However, based on the Dual-process theory, the IAT does not rely entirely on the automatic process; it is also influenced by a controlled process. The present study, therefore, analyzed the IAT data with the Quad model, separating four processes on the IAT performance: the likelihood that automatic association is activated by the stimulus in the trial (AC); that a correct response is discriminated in the trial (D); that the automatic bias is overcome in favor of a deliberate response (OB); and that when the association is not activated, and the individual fails to discriminate a correct answer, there is a guessing or response bias drives the response (G). The AC and G processes are automatic, while the D and OB processes are controlled. The AC parameter is considered as the strength of the association activated by the stimulus, which reflects what implicit measures of social cognition aim to assess. The stronger the automatic association between self and positive valence, the more likely it will be activated by a relevant stimulus. Therefore, the AC parameter was used as the index of implicit self-esteem in the present study. Meanwhile, the relationship between implicit self-esteem and depression is not fully investigated. In the cognitive theory of depression, it is assumed that the negative self-schema is crucial in depression. Based on this point of view, implicit self-esteem would be negatively associated with depression. However, the results among empirical studies are inconsistent. The aims of the present study were to examine the psychometric properties of the AC (i.e., test-retest reliability and its correlations with explicit self-esteem and depression) and compare it with that of the IAT effect. The present study had 105 patients with depressive disorders completing the Rosenberg Self-Esteem Scale, Beck Depression Inventory-II and the IAT on the pretest. After at least 3 weeks, the participants completed the second IAT. The data were analyzed by the latent-trait multinomial processing tree model (latent-trait MPT) with the TreeBUGS package in R. The result showed that the latent-trait MPT had a satisfactory model fit. The effect size of test-retest reliability of the AC and the IAT effect were medium (r = .43, p < .0001) and small (r = .29, p < .01) respectively. Only the AC showed a significant correlation with explicit self-esteem (r = .19, p < .05). Neither of the two indexes was correlated with depression. Collectively, the AC parameter was a satisfactory index of implicit self-esteem compared with the IAT effect. Also, the present study supported the results that implicit self-esteem was not correlated with depression.

Keywords: cognitive modeling, implicit association test, implicit self-esteem, quad model

Procedia PDF Downloads 94